摘要
为实现聚甲基丙烯酸甲酯(PMMA)微通道智能化激光加工,采用CO_(2)激光器研究激光功率密度、扫描速度和扫描次数对PMMA微通道深度和宽度的影响。基于BP(back propagation)神经网络建立激光加工工艺参数的预测模型,采用实验数据进行网络训练,并通过粒子群优化算法进行寻优。结果表明,所建立的神经网络优化模型可以使PMMA微通道宽度加工误差控制在5%以内,深度加工误差控制在12%以内,具有良好的预测精度,将为智能化PMMA微通道激光加工参数选取提供依据。
This study investigates the intelligent laser processing of polymethylmethacrylate(PMMA)microchannels,examining the influence of laser power density,scanning speed,and scanning passes on channel dimensions utilizing a CO_(2)laser.A back propagation(BP)neural network model was developed to predict the laser processing parameters.The model was trained with empirical data and further optimized using aparticle swarm optimization algorithm.The results showed that the neural network optimization model can control the PMMA microchannel width machining error within 5%and the depth machining error within 12%.The model has good prediction accuracy and will provide a basis for the intelligent selection of laser processing parameters of PMMA microchannel.
作者
张瑶
张秀丽
郑宏宇
王铭洋
魏娟
Zhang Yao;Zhang Xiuli;Zheng Hongyu;Wang Mingyang;Wei Juan(School of Mechanical Engineering,Shandong University of Technology,Zibo 255000,Shandong,China;Shandong Provincial Key Laboratory of Precision Manufacturing and Non-traditional Machining,Zibo 255000,Shandong,China)
出处
《应用激光》
CSCD
北大核心
2024年第5期98-105,共8页
Applied Laser
基金
国家重点研发计划政府间重点专项(2022YFE0199100)
国家自然科学基金(51905317)
山东省自然科学基金(ZR2020ME047)。
关键词
激光加工
微通道
BP神经网络
粒子群算法
laser processing
microchannel
back propagation neural network
particle swarm optimization
